Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    losing proposition or battle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diaria
    0.41
     url
    0.40
     trase
    0.38
    兴奋
    0.36
    Ր
    0.35
     jordan
    0.35
     mieux
    0.35
    invoke
    0.34
     пя
    0.34
     junto
    0.34
    POSITIVE LOGITS
    のかもし
    0.38
    ufact
    0.38
     Buildable
    0.38
    ීය
    0.38
     ತೋ
    0.37
    クター
    0.36
    0.36
     ഹാ
    0.36
     बनाता
    0.35
     வேளா
    0.35
    Act Density 0.000%

    No Known Activations